© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109198
    Prev
    Next
    INDEX
    Explanations

    people's states and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anyone
    -1.16
     someone
    -1.10
    一名
    -1.06
     anybody
    -1.01
     everyone
    -0.97
     any
    -0.97
     Rücksicht
    -0.95
    .}(
    -0.94
     Schwierigkeiten
    -0.94
     lecteurs
    -0.94
    POSITIVE LOGITS
     themselves
    1.43
     their
    1.36
     различни
    1.13
     berbagai
    1.13
     diferentes
    1.13
     différentes
    1.12
     rů
    1.12
     calorías
    1.12
     différents
    1.10
     forskellige
    1.08
    Activations Density 0.057%

    No Known Activations